mlsanityData to 14 Oct 2026

C3M: Cross-Session Multimodal Memory Maintenance for Long-Horizon Tasks

arXiv 2609.29735 ↗First posted 24 Sep 2026cs.AI cs.CL cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Long-horizon tasks require preserving and later recovering cross-session evidence under a bounded, query-blind memory budget. Existing compression can discard fine-grained visual cues or conflate semantically similar but incompatible observations. We present C3M, a cross-session multimodal memory organization that maintains a bounded active index over persistent source text-image evidence. Relation-aware updates consolidate safe redundancy while preserving complementary and incompatible records. At query time, budgeted routing selects useful index pages and expands their associated source evidence under a fixed reader budget. Together, these mechanisms establish a compact, provenance-preserving multimodal memory organization for cross-session long-horizon tasks, retaining temporal distinctions and source links required for reliable downstream reasoning. Code is available at https://github.com/HuzhouNLP/C3M.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 21 references that are in the map. First posted on arXiv 24 Sep 2026.

Builds on

17 of 21 references.

References · 17

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  3. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  4. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  5. 2023MovieChat: From Dense Token to Sparse Memory for Long Video Understandingcited by 542
  6. 2024HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Modelscited by 281
  7. 2023Augmenting Language Models with Long-Term Memorycited by 189
  8. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 141
  9. 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agentscited by 106
  10. 2024Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmarkcited by 55
  11. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agentscited by 48
  12. 2026From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agentscited by 15
5 more
  1. 2026MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Modelscited by 7
  2. 2026MemRefine: LLM-Guided Compression for Long-Term Agent Memorycited by 7
  3. 2026Towards a Dynamic and Fixed-budget Memory Bank for Efficient Streaming Video Understandingcited by 4
  4. 2026V-Mem: Modality-Routed Retrieval for Long-Term Multimodal Agentic Memorycited by 4
  5. 2026Memory Is Not Always Needed: Characterizing Conditional Memory in Scientific Reasoningcited by 1

Built on by

Not cited yet.